AI Agentic for Asset Managers SDLC Demo New York USA London UK Munich
Germany Zug Switzerland

Demo ­ Agentic AI in Enterprise SDLC ·Industry: Asset management ·Use
Case: Agentic AI Acceleration ·Scenario: External Data Feeds onboarding
and Holding's report update ·Pain Today: 1-month SDLC, many manual
hand-offs, duplicated effort ·Solution: AILA Agentic AI - role-specific
·Outcome: Faster delivery, higher data quality, lower cost /2

01 Use Case overview

Use Case: New Data Feed Integration

This case is typical for Asset Managers when the Team needs to extend an
existing report with attributes that will become available after
onboarding a new dataset. Using a role-specific AI agent and the AILA
framework, we can perform the following tasks with minimal human
involvement and development efforts:

üBuild a complete, INVEST-ready Jira ticket üUpdate documentation on
Confluence page üNew data feed integration üData processing üStored
procedure (SP) update üTesting üRelease /4

Use Case: New Data Feed Integration

External Provider Contracts Data

RAW Storage Contracts Data

Preprocessing &Validation

Instruments Data Positions Data

Positions Report

Instruments and Positions data

/5

02 How does it work

SDLC Empowered by AILA + Amazon Q

With Amazon Q at the core of our Agentic AI stack, every stage of this
change request was automated inside the tools you already use:

Q-powered BA Agent · built a complete, INVEST-ready Jira ticket.

Q-driven Design Agent · generated all AILAcompliant configs,
documentation, and a GitLab merge request validated and ready for
review.

Q-based QA and Deployment agents ·will now run the full test suite and
promote the artefacts through our release pipeline, updating CAB records
automatically.

The net result: a 1-month cycle compresses to 5-7 days, with higher data
quality and full traceability - thanks to Amazon Q's generative power
fueling each agent. /7

03 How much time does it save

Roles in a Typical Change Request

Phase / Role Product Owner / BA Data Architect Data Engineer QA Engineer
DevOps / Release Total

Key Work / Responsibility Capture requirement, draft user story & AC
Design raw table & customer mapping Update source stage, transform
logic, unit tests Regression & data-quality testing Promote artifacts,
handle CAB & production release Full SDLC for a new Data Feed onboarding

Main Deliverables INVEST-ready story, data dictionaries DDL script,
mapping specification Source + transform code, automated test suite
Automated regression / DQ results CI/CD pipeline run, deployment report

Typical Effort\* 3 days 2 days 5 days 5 days 5 days 20 days /9

Agentic Acceleration

Human Role Product Owner / BA Data Architect / Tech Lead Data Engineer
QA Engineer DevOps / Release Full Change Request

Typical Effort\*

AILA Agent

3 days 5 days 5-10 days 5 days 5 days

StoryCraft-BA generates INVEST-ready story, data dictionaries, gap
checks Generalates and validates design, implementation and
documentation PipeCoder-Dev scaffolds Glue source & transform jobs,
builds unit tests, enforces coding standards TestGuard-QA auto-generates
regression & DQ checks, parameterizes test data AutoDeploy-Ops builds,
tags, promotes artifacts, prepares CAB documentation

20days

All agents above working in concert

Effort with AILA\* 2-4 hours 1 hour ­ 1 day, depends on change complexity
2 hours ­ 3 days up to 2 days 1 day 3-7 days

Time Saved 80% 80 % 70 % 60 % 80 % 60 - 75 % / 10

04 Live demo